FinMarBa: A Market-Informed Dataset for Financial Sentiment Classification
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909712675504128 |
|---|---|
| author | Lefort, Baptiste Benhamou, Eric Guez, Beatrice Ohana, Jean-Jacques Setrouk, Ethan Etienne, Alban |
| author_facet | Lefort, Baptiste Benhamou, Eric Guez, Beatrice Ohana, Jean-Jacques Setrouk, Ethan Etienne, Alban |
| contents | This paper presents a novel hierarchical framework for portfolio optimization, integrating lightweight Large Language Models (LLMs) with Deep Reinforcement Learning (DRL) to combine sentiment signals from financial news with traditional market indicators. Our three-tier architecture employs base RL agents to process hybrid data, meta-agents to aggregate their decisions, and a super-agent to merge decisions based on market data and sentiment analysis. Evaluated on data from 2018 to 2024, after training on 2000-2017, the framework achieves a 26% annualized return and a Sharpe ratio of 1.2, outperforming equal-weighted and S&P 500 benchmarks. Key contributions include scalable cross-modal integration, a hierarchical RL structure for enhanced stability, and open-source reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22932 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FinMarBa: A Market-Informed Dataset for Financial Sentiment Classification Lefort, Baptiste Benhamou, Eric Guez, Beatrice Ohana, Jean-Jacques Setrouk, Ethan Etienne, Alban Computation and Language General Finance This paper presents a novel hierarchical framework for portfolio optimization, integrating lightweight Large Language Models (LLMs) with Deep Reinforcement Learning (DRL) to combine sentiment signals from financial news with traditional market indicators. Our three-tier architecture employs base RL agents to process hybrid data, meta-agents to aggregate their decisions, and a super-agent to merge decisions based on market data and sentiment analysis. Evaluated on data from 2018 to 2024, after training on 2000-2017, the framework achieves a 26% annualized return and a Sharpe ratio of 1.2, outperforming equal-weighted and S&P 500 benchmarks. Key contributions include scalable cross-modal integration, a hierarchical RL structure for enhanced stability, and open-source reproducibility. |
| title | FinMarBa: A Market-Informed Dataset for Financial Sentiment Classification |
| topic | Computation and Language General Finance |
| url | https://arxiv.org/abs/2507.22932 |